巨魔农场中的视觉识别：Twitter审核研究联盟

IF 5.5 1区文学 Q1 COMMUNICATION

Social Media + Society Pub Date : 2025-03-24 DOI:10.1177/20563051251323652

Marco Bastos

{"title":"巨魔农场中的视觉识别：Twitter审核研究联盟","authors":"Marco Bastos","doi":"10.1177/20563051251323652","DOIUrl":null,"url":null,"abstract":"The Twitter Moderation Research Consortium is a database of network propaganda and influence operations that includes 115,474 unique Twitter accounts, millions of tweets, and over one terabyte of media removed from the platform between 2017 and 2022. We probe this database using Google’s Vision API and Keras with TensorFlow to test whether foreign influence operations can be identified based on the visual presentation of fake user profiles emphasizing gender, race, camera angle, sensuality, and emotion. Our results show that sensuality is a variable associated with operations that replicate the Kremlin-linked Internet Research Agency campaign, being particularly prevalent in influence operations that targeted communities in North and South America, but also in Indonesia, Turkey, and Pakistan. Our results also show that the visual identities of fake social media profiles are predictive of influence operations given their reliance on selfies, sensual young women, K-pop aesthetics, or alternatively nationalistic iconography overlaid with text to convey ideological positioning.","PeriodicalId":47920,"journal":{"name":"Social Media + Society","volume":"64 1","pages":""},"PeriodicalIF":5.5000,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Visual Identities in Troll Farms: The Twitter Moderation Research Consortium\",\"authors\":\"Marco Bastos\",\"doi\":\"10.1177/20563051251323652\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Twitter Moderation Research Consortium is a database of network propaganda and influence operations that includes 115,474 unique Twitter accounts, millions of tweets, and over one terabyte of media removed from the platform between 2017 and 2022. We probe this database using Google’s Vision API and Keras with TensorFlow to test whether foreign influence operations can be identified based on the visual presentation of fake user profiles emphasizing gender, race, camera angle, sensuality, and emotion. Our results show that sensuality is a variable associated with operations that replicate the Kremlin-linked Internet Research Agency campaign, being particularly prevalent in influence operations that targeted communities in North and South America, but also in Indonesia, Turkey, and Pakistan. Our results also show that the visual identities of fake social media profiles are predictive of influence operations given their reliance on selfies, sensual young women, K-pop aesthetics, or alternatively nationalistic iconography overlaid with text to convey ideological positioning.\",\"PeriodicalId\":47920,\"journal\":{\"name\":\"Social Media + Society\",\"volume\":\"64 1\",\"pages\":\"\"},\"PeriodicalIF\":5.5000,\"publicationDate\":\"2025-03-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Social Media + Society\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1177/20563051251323652\",\"RegionNum\":1,\"RegionCategory\":\"文学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMMUNICATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Social Media + Society","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1177/20563051251323652","RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMMUNICATION","Score":null,"Total":0}

引用次数: 0

摘要

推特审核研究联盟是一个网络宣传和影响操作的数据库，其中包括115,474个独立推特账户，数百万条推文，以及2017年至2022年间从平台上删除的超过1tb的媒体。我们使用谷歌的视觉API和带有TensorFlow的Keras来探测这个数据库，以测试是否可以基于强调性别、种族、相机角度、性感和情感的虚假用户档案的视觉呈现来识别外国影响操作。我们的研究结果表明，性感是与复制克里姆林宫相关的互联网研究机构活动相关的一个变量，在针对北美和南美社区以及印度尼西亚、土耳其和巴基斯坦社区的影响力行动中尤其普遍。我们的研究结果还表明，虚假社交媒体个人资料的视觉身份可以预测影响操作，因为它们依赖于自拍、性感的年轻女性、韩国流行音乐美学，或者是用文字覆盖的民族主义图像来传达意识形态定位。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Visual Identities in Troll Farms: The Twitter Moderation Research Consortium

The Twitter Moderation Research Consortium is a database of network propaganda and influence operations that includes 115,474 unique Twitter accounts, millions of tweets, and over one terabyte of media removed from the platform between 2017 and 2022. We probe this database using Google’s Vision API and Keras with TensorFlow to test whether foreign influence operations can be identified based on the visual presentation of fake user profiles emphasizing gender, race, camera angle, sensuality, and emotion. Our results show that sensuality is a variable associated with operations that replicate the Kremlin-linked Internet Research Agency campaign, being particularly prevalent in influence operations that targeted communities in North and South America, but also in Indonesia, Turkey, and Pakistan. Our results also show that the visual identities of fake social media profiles are predictive of influence operations given their reliance on selfies, sensual young women, K-pop aesthetics, or alternatively nationalistic iconography overlaid with text to convey ideological positioning.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Social Media + Society COMMUNICATION-

CiteScore

9.20

自引率

3.80%

发文量

111

审稿时长

12 weeks

期刊介绍： Social Media + Society is an open access, peer-reviewed scholarly journal that focuses on the socio-cultural, political, psychological, historical, economic, legal and policy dimensions of social media in societies past, contemporary and future. We publish interdisciplinary work that draws from the social sciences, humanities and computational social sciences, reaches out to the arts and natural sciences, and we endorse mixed methods and methodologies. The journal is open to a diversity of theoretic paradigms and methodologies. The editorial vision of Social Media + Society draws inspiration from research on social media to outline a field of study poised to reflexively grow as social technologies evolve. We foster the open access of sharing of research on the social properties of media, as they manifest themselves through the uses people make of networked platforms past and present, digital and non. The journal presents a collaborative, open, and shared space, dedicated exclusively to the study of social media and their implications for societies. It facilitates state-of-the-art research on cutting-edge trends and allows scholars to focus and track trends specific to this field of study.